boris commited on
Commit
3d38395
1 Parent(s): 7fef8a5

New model from https://wandb.ai/wandb/huggingtweets/runs/1wp396eq

Browse files
Files changed (6) hide show
  1. README.md +25 -15
  2. config.json +2 -1
  3. flax_model.msgpack +0 -3
  4. pytorch_model.bin +1 -1
  5. tokenizer.json +0 -0
  6. training_args.bin +2 -2
README.md CHANGED
@@ -1,17 +1,27 @@
1
  ---
2
  language: en
3
- thumbnail: https://www.huggingtweets.com/justinbieber/1618155789125/predictions.png
4
  tags:
5
  - huggingtweets
6
  widget:
7
  - text: "My dream is"
8
  ---
9
 
10
- <div>
11
- <div style="width: 132px; height:132px; border-radius: 50%; background-size: cover; background-image: url('https://pbs.twimg.com/profile_images/1365346288657715201/lRfQRoWl_400x400.jpg')">
12
- </div>
13
- <div style="margin-top: 8px; font-size: 19px; font-weight: 800">Justin Bieber 🤖 AI Bot </div>
14
- <div style="font-size: 15px">@justinbieber bot</div>
 
 
 
 
 
 
 
 
 
 
15
  </div>
16
 
17
  I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
@@ -28,24 +38,24 @@ To understand how the model was developed, check the [W&B report](https://wandb.
28
 
29
  ## Training data
30
 
31
- The model was trained on [@justinbieber's tweets](https://twitter.com/justinbieber).
32
 
33
- | Data | Quantity |
34
  | --- | --- |
35
- | Tweets downloaded | 3149 |
36
- | Retweets | 1028 |
37
- | Short tweets | 858 |
38
- | Tweets kept | 1263 |
39
 
40
- [Explore the data](https://wandb.ai/wandb/huggingtweets/runs/3s26rtnl/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
41
 
42
  ## Training procedure
43
 
44
  The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @justinbieber's tweets.
45
 
46
- Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/3eqg2ygn) for full transparency and reproducibility.
47
 
48
- At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/3eqg2ygn/artifacts) is logged and versioned.
49
 
50
  ## How to use
51
 
 
1
  ---
2
  language: en
3
+ thumbnail: https://github.com/borisdayma/huggingtweets/blob/master/img/logo.png?raw=true
4
  tags:
5
  - huggingtweets
6
  widget:
7
  - text: "My dream is"
8
  ---
9
 
10
+ <div class="inline-flex flex-col" style="line-height: 1.5;">
11
+ <div class="flex">
12
+ <div
13
+ style="display:inherit; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url(&#39;https://pbs.twimg.com/profile_images/1365346288657715201/lRfQRoWl_400x400.jpg&#39;)">
14
+ </div>
15
+ <div
16
+ style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url(&#39;&#39;)">
17
+ </div>
18
+ <div
19
+ style="display:none; margin-left: 4px; margin-right: 4px; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url(&#39;&#39;)">
20
+ </div>
21
+ </div>
22
+ <div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 AI BOT 🤖</div>
23
+ <div style="text-align: center; font-size: 16px; font-weight: 800">Justin Bieber</div>
24
+ <div style="text-align: center; font-size: 14px;">@justinbieber</div>
25
  </div>
26
 
27
  I was made with [huggingtweets](https://github.com/borisdayma/huggingtweets).
 
38
 
39
  ## Training data
40
 
41
+ The model was trained on tweets from Justin Bieber.
42
 
43
+ | Data | Justin Bieber |
44
  | --- | --- |
45
+ | Tweets downloaded | 3166 |
46
+ | Retweets | 1034 |
47
+ | Short tweets | 863 |
48
+ | Tweets kept | 1269 |
49
 
50
+ [Explore the data](https://wandb.ai/wandb/huggingtweets/runs/33sw8hgs/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
51
 
52
  ## Training procedure
53
 
54
  The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on @justinbieber's tweets.
55
 
56
+ Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/wandb/huggingtweets/runs/1wp396eq) for full transparency and reproducibility.
57
 
58
+ At the end of training, [the final model](https://wandb.ai/wandb/huggingtweets/runs/1wp396eq/artifacts) is logged and versioned.
59
 
60
  ## How to use
61
 
config.json CHANGED
@@ -19,6 +19,7 @@
19
  "n_layer": 12,
20
  "n_positions": 1024,
21
  "resid_pdrop": 0.1,
 
22
  "summary_activation": null,
23
  "summary_first_dropout": 0.1,
24
  "summary_proj_to_labels": true,
@@ -34,7 +35,7 @@
34
  "top_p": 0.95
35
  }
36
  },
37
- "transformers_version": "4.5.0",
38
  "use_cache": true,
39
  "vocab_size": 50257
40
  }
 
19
  "n_layer": 12,
20
  "n_positions": 1024,
21
  "resid_pdrop": 0.1,
22
+ "scale_attn_weights": true,
23
  "summary_activation": null,
24
  "summary_first_dropout": 0.1,
25
  "summary_proj_to_labels": true,
 
35
  "top_p": 0.95
36
  }
37
  },
38
+ "transformers_version": "4.6.1",
39
  "use_cache": true,
40
  "vocab_size": 50257
41
  }
flax_model.msgpack DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c49d1872fb84d9b14078e0aadcf70f55b2696f4e4cc1f5ea384f55bd17f276a
3
- size 497764120
 
 
 
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7a7b5490a9a56fe69d2150796d9f28417fc201da7179dff583889a1248fefc13
3
  size 510408315
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f11d2b2211bdb6b242ac4eb7aa3485aa876da3c4e1ca739147ec84f0821386d9
3
  size 510408315
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:913f2dde9d02ce9a334b9a756e27f748e74aa0d32563f27598a40a64d6a01b0d
3
- size 2351
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e825d02968394c9e950b5463095549b40f5bff332ff26be872663029de4048e
3
+ size 2415